© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52354
    Prev
    Next
    INDEX
    Explanations

    federal irrigation contracts, xarray plotting, programmatic IDs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĩĨ
    -0.12
    æīĵæĸŃ
    -0.11
    åħ±äº«åįķ车
    -0.10
    严åİī
    -0.09
    ä¸¥æł¼çļĦ
    -0.09
    banks
    -0.09
    æĮ¥æīĭ
    -0.09
    pitch
    -0.09
     apt
    -0.08
    æĶ¾å®½
    -0.08
    POSITIVE LOGITS
     Horde
    0.09
    .DOM
    0.09
    ä¸Ģ大
    0.08
     placeholders
    0.08
    èµĦ产è¯Ħä¼°
    0.08
     __("
    0.08
    åĬ¼
    0.08
    åĭį
    0.08
    åĿŀ
    0.08
    abit
    0.08
    Activations Density 0.054%

    No Known Activations